© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103013
    Prev
    Next
    INDEX
    Explanations

    temporary or transient

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on content words detailing bureaucratic roles and actions (e.g. “short‐lived,” “officials,” “collecting,” “sustaining”)—in other words, it detects descriptive terms about administrative or historical processes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кою
    -0.88
     SLOW
    -0.88
    igerung
    -0.84
    延迟
    -0.81
    hace
    -0.80
    ✚
    -0.79
     FEE
    -0.79
     пові
    -0.78
     ftill
    -0.77
     SILVA
    -0.77
    POSITIVE LOGITS
     temporary
    2.94
     transient
    2.75
     ephemeral
    2.53
     fleeting
    2.36
    temporary
    2.33
     transitory
    2.30
    Temporary
    2.22
    transient
    2.20
    Transient
    2.19
     Temporary
    2.13
    Activations Density 0.102%

    No Known Activations